Retether to Keras v3.6.0

.tether/man/activation_elu.txt

@@ -3,7 +3,7 @@ keras.activations.elu(x, alpha=1.0)
 __doc__
 Exponential Linear Unit.
 
-The exponential linear unit (ELU) with `alpha > 0` is define as:
+The exponential linear unit (ELU) with `alpha > 0` is defined as:
 
 - `x` if `x > 0`
 - alpha * `exp(x) - 1` if `x < 0`
@@ -23,3 +23,4 @@ Args:
 Reference:
 
 - [Clevert et al., 2016](https://arxiv.org/abs/1511.07289)
+

.tether/man/application_densenet121.txt

@@ -53,7 +53,7 @@ Args:
             be applied.
     classes: optional number of classes to classify images
         into, only to be specified if `include_top` is `True`, and
-        if no `weights` argument is specified.
+        if no `weights` argument is specified. Defaults to 1000.
     classifier_activation: A `str` or callable.
         The activation function to use
         on the "top" layer. Ignored unless `include_top=True`. Set

.tether/man/application_densenet169.txt

@@ -53,7 +53,7 @@ Args:
             be applied.
     classes: optional number of classes to classify images
         into, only to be specified if `include_top` is `True`, and
-        if no `weights` argument is specified.
+        if no `weights` argument is specified. Defaults to 1000.
     classifier_activation: A `str` or callable.
         The activation function to use
         on the "top" layer. Ignored unless `include_top=True`. Set

.tether/man/application_densenet201.txt

@@ -53,7 +53,7 @@ Args:
             be applied.
     classes: optional number of classes to classify images
         into, only to be specified if `include_top` is `True`, and
-        if no `weights` argument is specified.
+        if no `weights` argument is specified. Defaults to 1000.
     classifier_activation: A `str` or callable.
         The activation function to use
         on the "top" layer. Ignored unless `include_top=True`. Set

.tether/man/application_resnet101.txt

@@ -53,7 +53,7 @@ Args:
         - `max` means that global max pooling will be applied.
     classes: optional number of classes to classify images into, only to be
         specified if `include_top` is `True`, and if no `weights` argument is
-        specified.
+        specified. Defaults to `1000`.
     classifier_activation: A `str` or callable. The activation function to
         use on the "top" layer. Ignored unless `include_top=True`. Set
         `classifier_activation=None` to return the logits of the "top" layer.

.tether/man/application_resnet152.txt

@@ -53,7 +53,7 @@ Args:
         - `max` means that global max pooling will be applied.
     classes: optional number of classes to classify images into, only to be
         specified if `include_top` is `True`, and if no `weights` argument is
-        specified.
+        specified. Defaults to `1000`.
     classifier_activation: A `str` or callable. The activation function to
         use on the "top" layer. Ignored unless `include_top=True`. Set
         `classifier_activation=None` to return the logits of the "top" layer.

.tether/man/application_resnet50.txt

@@ -53,7 +53,7 @@ Args:
         - `max` means that global max pooling will be applied.
     classes: optional number of classes to classify images into, only to be
         specified if `include_top` is `True`, and if no `weights` argument is
-        specified.
+        specified. Defaults to `1000`.
     classifier_activation: A `str` or callable. The activation function to
         use on the "top" layer. Ignored unless `include_top=True`. Set
         `classifier_activation=None` to return the logits of the "top" layer.

.tether/man/application_xception.txt

@@ -59,7 +59,7 @@ Args:
             be applied.
     classes: optional number of classes to classify images
         into, only to be specified if `include_top` is `True`, and
-        if no `weights` argument is specified.
+        if no `weights` argument is specified. Defaults to `1000`.
     classifier_activation: A `str` or callable. The activation function to
         use on the "top" layer. Ignored unless `include_top=True`. Set
         `classifier_activation=None` to return the logits of the "top"

.tether/man/clone_model.txt

@@ -87,7 +87,7 @@ def clone_function(layer):
         config["seed"] = 1337
     return layer.__class__.from_config(config)
 
-new_model = clone_model(model)
+new_model = clone_model(model, clone_function=clone_function)
 ```
 
 Using a `call_function` to add a `Dropout` layer after each `Dense` layer

.tether/man/export_savedmodel.keras.src.models.model.Model.txt

@@ -2,7 +2,8 @@ __signature__
 keras.Model.export(
   self,
   filepath,
-  format='tf_saved_model'
+  format='tf_saved_model',
+  verbose=True
 )
 __doc__
 Create a TF SavedModel artifact for inference.
@@ -22,6 +23,7 @@ entirely standalone.
 Args:
     filepath: `str` or `pathlib.Path` object. Path where to save
         the artifact.
+    verbose: whether to print all the variables of the exported model.
 
 Example:
 

.tether/man/get_file.txt

@@ -35,14 +35,18 @@ path_to_downloaded_file = get_file(
 ```
 
 Args:
-    fname: Name of the file. If an absolute path, e.g. `"/path/to/file.txt"`
-        is specified, the file will be saved at that location.
+    fname: If the target is a single file, this is your desired
+        local name for the file.
         If `None`, the name of the file at `origin` will be used.
+        If downloading and extracting a directory archive,
+        the provided `fname` will be used as extraction directory
+        name (only if it doesn't have an extension).
     origin: Original URL of the file.
     untar: Deprecated in favor of `extract` argument.
-        boolean, whether the file should be decompressed
+        Boolean, whether the file is a tar archive that should
+        be extracted.
     md5_hash: Deprecated in favor of `file_hash` argument.
-        md5 hash of the file for verification
+        md5 hash of the file for file integrity verification.
     file_hash: The expected hash string of the file after download.
         The sha256 and md5 hash algorithms are both supported.
     cache_subdir: Subdirectory under the Keras cache dir where the file is
@@ -51,7 +55,8 @@ Args:
     hash_algorithm: Select the hash algorithm to verify the file.
         options are `"md5'`, `"sha256'`, and `"auto'`.
         The default 'auto' detects the hash algorithm in use.
-    extract: True tries extracting the file as an Archive, like tar or zip.
+    extract: If `True`, extracts the archive. Only applicable to compressed
+        archive files like tar or zip.
     archive_format: Archive format to try for extracting the file.
         Options are `"auto'`, `"tar'`, `"zip'`, and `None`.
         `"tar"` includes tar, tar.gz, and tar.bz files.

.tether/man/get_state_tree.txt

@@ -0,0 +1,67 @@
+__signature__
+keras.Model.get_state_tree(self, value_format='backend_tensor')
+__doc__
+Retrieves tree-like structure of model variables.
+
+This method allows retrieval of different model variables (trainable,
+non-trainable, optimizer, and metrics). The variables are returned in a
+nested dictionary format, where the keys correspond to the variable
+names and the values are the nested representations of the variables.
+
+Returns:
+    dict: A dictionary containing the nested representations of the
+        requested variables. The keys are the variable names, and the
+        values are the corresponding nested dictionaries.
+    value_format: One of `"backend_tensor"`, `"numpy_array"`.
+        The kind of array to return as the leaves of the nested
+            state tree.
+
+Example:
+
+```python
+model = keras.Sequential([
+    keras.Input(shape=(1,), name="my_input"),
+    keras.layers.Dense(1, activation="sigmoid", name="my_dense"),
+], name="my_sequential")
+model.compile(optimizer="adam", loss="mse", metrics=["mae"])
+model.fit(np.array([[1.0]]), np.array([[1.0]]))
+state_tree = model.get_state_tree()
+```
+
+The `state_tree` dictionary returned looks like:
+
+```
+{
+    'metrics_variables': {
+        'loss': {
+            'count': ...,
+            'total': ...,
+        },
+        'mean_absolute_error': {
+            'count': ...,
+            'total': ...,
+        }
+    },
+    'trainable_variables': {
+        'my_sequential': {
+            'my_dense': {
+                'bias': ...,
+                'kernel': ...,
+            }
+        }
+    },
+    'non_trainable_variables': {},
+    'optimizer_variables': {
+        'adam': {
+                'iteration': ...,
+                'learning_rate': ...,
+                'my_sequential_my_dense_bias_momentum': ...,
+                'my_sequential_my_dense_bias_velocity': ...,
+                'my_sequential_my_dense_kernel_momentum': ...,
+                'my_sequential_my_dense_kernel_velocity': ...,
+            }
+        }
+    }
+}
+```
+

.tether/man/initializer_glorot_normal.txt

@@ -37,6 +37,7 @@ class GlorotNormal(VarianceScaling)
  |  Method resolution order:
  |      GlorotNormal
  |      VarianceScaling
+ |      RandomInitializer
  |      keras.src.initializers.initializer.Initializer
  |      builtins.object
  |
@@ -51,3 +52,4 @@ class GlorotNormal(VarianceScaling)
  |      Returns:
  |          A JSON-serializable Python dict.
  |
+

.tether/man/initializer_glorot_uniform.txt

@@ -36,6 +36,7 @@ class GlorotUniform(VarianceScaling)
  |  Method resolution order:
  |      GlorotUniform
  |      VarianceScaling
+ |      RandomInitializer
  |      keras.src.initializers.initializer.Initializer
  |      builtins.object
  |
@@ -50,3 +51,4 @@ class GlorotUniform(VarianceScaling)
  |      Returns:
  |          A JSON-serializable Python dict.
  |
+

.tether/man/initializer_he_normal.txt

@@ -36,6 +36,7 @@ class HeNormal(VarianceScaling)
  |  Method resolution order:
  |      HeNormal
  |      VarianceScaling
+ |      RandomInitializer
  |      keras.src.initializers.initializer.Initializer
  |      builtins.object
  |
@@ -50,3 +51,4 @@ class HeNormal(VarianceScaling)
  |      Returns:
  |          A JSON-serializable Python dict.
  |
+

.tether/man/initializer_he_uniform.txt

@@ -36,6 +36,7 @@ class HeUniform(VarianceScaling)
  |  Method resolution order:
  |      HeUniform
  |      VarianceScaling
+ |      RandomInitializer
  |      keras.src.initializers.initializer.Initializer
  |      builtins.object
  |
@@ -50,3 +51,4 @@ class HeUniform(VarianceScaling)
  |      Returns:
  |          A JSON-serializable Python dict.
  |
+

.tether/man/initializer_lecun_normal.txt

@@ -40,6 +40,7 @@ class LecunNormal(VarianceScaling)
  |  Method resolution order:
  |      LecunNormal
  |      VarianceScaling
+ |      RandomInitializer
  |      keras.src.initializers.initializer.Initializer
  |      builtins.object
  |
@@ -54,3 +55,4 @@ class LecunNormal(VarianceScaling)
  |      Returns:
  |          A JSON-serializable Python dict.
  |
+

.tether/man/initializer_lecun_uniform.txt

@@ -36,6 +36,7 @@ class LecunUniform(VarianceScaling)
  |  Method resolution order:
  |      LecunUniform
  |      VarianceScaling
+ |      RandomInitializer
  |      keras.src.initializers.initializer.Initializer
  |      builtins.object
  |
@@ -50,3 +51,4 @@ class LecunUniform(VarianceScaling)
  |      Returns:
  |          A JSON-serializable Python dict.
  |
+

.tether/man/initializer_orthogonal.txt

@@ -1,6 +1,6 @@
 Help on class OrthogonalInitializer in module keras.src.initializers.random_initializers:
 
-class OrthogonalInitializer(keras.src.initializers.initializer.Initializer)
+class OrthogonalInitializer(RandomInitializer)
  |  OrthogonalInitializer(gain=1.0, seed=None)
  |
  |  Initializer that generates an orthogonal matrix.
@@ -37,6 +37,7 @@ class OrthogonalInitializer(keras.src.initializers.initializer.Initializer)
  |
  |  Method resolution order:
  |      OrthogonalInitializer
+ |      RandomInitializer
  |      keras.src.initializers.initializer.Initializer
  |      builtins.object
  |
@@ -66,3 +67,4 @@ class OrthogonalInitializer(keras.src.initializers.initializer.Initializer)
  |      Returns:
  |          A JSON-serializable Python dict.
  |
+

.tether/man/initializer_random_normal.txt

@@ -1,6 +1,6 @@
 Help on class RandomNormal in module keras.src.initializers.random_initializers:
 
-class RandomNormal(keras.src.initializers.initializer.Initializer)
+class RandomNormal(RandomInitializer)
  |  RandomNormal(mean=0.0, stddev=0.05, seed=None)
  |
  |  Random normal initializer.
@@ -33,6 +33,7 @@ class RandomNormal(keras.src.initializers.initializer.Initializer)
  |
  |  Method resolution order:
  |      RandomNormal
+ |      RandomInitializer
  |      keras.src.initializers.initializer.Initializer
  |      builtins.object
  |
@@ -63,3 +64,4 @@ class RandomNormal(keras.src.initializers.initializer.Initializer)
  |      Returns:
  |          A JSON-serializable Python dict.
  |
+

.tether/man/initializer_random_uniform.txt

@@ -1,6 +1,6 @@
 Help on class RandomUniform in module keras.src.initializers.random_initializers:
 
-class RandomUniform(keras.src.initializers.initializer.Initializer)
+class RandomUniform(RandomInitializer)
  |  RandomUniform(minval=-0.05, maxval=0.05, seed=None)
  |
  |  Random uniform initializer.
@@ -33,6 +33,7 @@ class RandomUniform(keras.src.initializers.initializer.Initializer)
  |
  |  Method resolution order:
  |      RandomUniform
+ |      RandomInitializer
  |      keras.src.initializers.initializer.Initializer
  |      builtins.object
  |
@@ -63,3 +64,4 @@ class RandomUniform(keras.src.initializers.initializer.Initializer)
  |      Returns:
  |          A JSON-serializable Python dict.
  |
+

.tether/man/initializer_truncated_normal.txt

@@ -1,6 +1,6 @@
 Help on class TruncatedNormal in module keras.src.initializers.random_initializers:
 
-class TruncatedNormal(keras.src.initializers.initializer.Initializer)
+class TruncatedNormal(RandomInitializer)
  |  TruncatedNormal(mean=0.0, stddev=0.05, seed=None)
  |
  |  Initializer that generates a truncated normal distribution.
@@ -36,6 +36,7 @@ class TruncatedNormal(keras.src.initializers.initializer.Initializer)
  |
  |  Method resolution order:
  |      TruncatedNormal
+ |      RandomInitializer
  |      keras.src.initializers.initializer.Initializer
  |      builtins.object
  |
@@ -66,3 +67,4 @@ class TruncatedNormal(keras.src.initializers.initializer.Initializer)
  |      Returns:
  |          A JSON-serializable Python dict.
  |
+

.tether/man/initializer_variance_scaling.txt

@@ -1,6 +1,6 @@
 Help on class VarianceScaling in module keras.src.initializers.random_initializers:
 
-class VarianceScaling(keras.src.initializers.initializer.Initializer)
+class VarianceScaling(RandomInitializer)
  |  VarianceScaling(scale=1.0, mode='fan_in', distribution='truncated_normal', seed=None)
  |
  |  Initializer that adapts its scale to the shape of its input tensors.
@@ -45,6 +45,7 @@ class VarianceScaling(keras.src.initializers.initializer.Initializer)
  |
  |  Method resolution order:
  |      VarianceScaling
+ |      RandomInitializer
  |      keras.src.initializers.initializer.Initializer
  |      builtins.object
  |
@@ -76,3 +77,4 @@ class VarianceScaling(keras.src.initializers.initializer.Initializer)
  |      Returns:
  |          A JSON-serializable Python dict.
  |
+